← Back to community benchmarks
Qwen3.6-35B-A3B-Holo3-Qwopus-mxfp4
Performance
16k
tokens
408.3
PP tok/s
37.4
TG tok/s
40125
TTFT (ms)
19.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 416.1 | 49.7 | 18.2 GB | view |
| 4k | 457.2 | 47.0 | 18.9 GB | view |
| 8k | 443.6 | 43.9 | 19.2 GB | view |
| 16k | 408.3 | 37.4 | 19.9 GB | current |
| 32k | 338.6 | 28.6 | 21.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.7 | 1.00× |
| 2× | 74.2 | 1.49× |
| 4× | 88.7 | 1.78× |